CN112802022A - Method for intelligently detecting defective glass image, electronic device and storage medium - Google Patents

Method for intelligently detecting defective glass image, electronic device and storage medium Download PDF

Info

Publication number
CN112802022A
CN112802022A CN202110398702.XA CN202110398702A CN112802022A CN 112802022 A CN112802022 A CN 112802022A CN 202110398702 A CN202110398702 A CN 202110398702A CN 112802022 A CN112802022 A CN 112802022A
Authority
CN
China
Prior art keywords
image
glass
processing
defect
defective
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110398702.XA
Other languages
Chinese (zh)
Other versions
CN112802022B (en
Inventor
陈奕舜
范伟华
邹伟金
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gaoshi Technology Suzhou Co ltd
Original Assignee
Huizhou Govion Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huizhou Govion Technology Co ltd filed Critical Huizhou Govion Technology Co ltd
Priority to CN202110398702.XA priority Critical patent/CN112802022B/en
Publication of CN112802022A publication Critical patent/CN112802022A/en
Application granted granted Critical
Publication of CN112802022B publication Critical patent/CN112802022B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators
    • G06T5/30Erosion or dilatation, e.g. thinning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/70Denoising; Smoothing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/187Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)

Abstract

The application relates to a method for intelligently detecting a defective glass image. The method comprises the following steps: acquiring a shot image of glass to be detected; carrying out image preprocessing on the shot image to obtain a preprocessed image; carrying out image segmentation processing on the preprocessed image to obtain a first glass image; if the first glass image has image defects, performing closed operation processing on the first glass image to obtain a second glass image; and subtracting the first glass image from the second glass image to obtain a defect glass image representing the shape of the defect. The scheme that this application provided detects cut glass edge image through automatic, has avoided the error that arouses by artifical measurement, can promote the product detection efficiency of glass production line, and then reduces the risk that leads to defective glass product to flow into market because of the cutting is uneven, improves product quality.

Description

Method for intelligently detecting defective glass image, electronic device and storage medium
Technical Field
The present disclosure relates to the field of defective glass image detection technologies, and in particular, to a method, an electronic device, and a storage medium for automatically detecting a defective glass image.
Background
Glass has been known for thousands of years and is one of the most widely used man-made materials in the high-tech field. In the screen display industry, liquid crystal is encapsulated in glass in a high-temperature and high-pressure mode to form a high-tech photoelectric glass product, namely liquid crystal glass. At present, Liquid Crystal glass is widely used as a light modulation device of electronic equipment, an upper polarizing plate and a lower polarizing plate are attached to a color film after a box forming process, and a Liquid Crystal Display (LCD for short) can be formed by adding backlight to the bottom of the Liquid Crystal glass, and is an important device of the current Display equipment.
In the Thin film transistor liquid crystal display (TFT-LCD) industry, because the production of a large-sized glass substrate can effectively improve the yield and the output rate of a large-screen liquid crystal panel, and simultaneously reduce the production cost, the glass substrate is always enlarged in the production process, and then cut according to the actual production requirement, four sides of the cut glass are required to be straight lines, which is an important control parameter in the glass production process; the precision cutter wheel is replaced and the glass substrate moves in the cutting process, the cutting linearity of the edge part can fluctuate, the local position of the edge part can be raised or sunken, the phenomena of fragment, under grinding, edge burning, cracks and the like can be caused, and the product quality is seriously influenced.
At present, the measurement mode of the defective glass is usually that people operate a vernier caliper or a quadratic element image measuring instrument to measure, and the measurement is carried out according to the four-side linearity measurement data.
Disclosure of Invention
In order to solve the problems in the related art, the method for intelligently detecting the defective glass image is provided, the method automatically processes and classifies the cut glass edge image by extracting the image of the glass edge to be detected, and then extracts the defective glass image, so that the defect type of the glass image can be accurately determined while the glass detection efficiency is improved.
The application provides a method for intelligently detecting a defective glass image in a first aspect, which comprises the following steps:
acquiring a shot image of glass to be detected; carrying out image preprocessing on the shot image to obtain a preprocessed image; carrying out image segmentation processing on the preprocessed image to obtain a first glass image, wherein the first glass image is a binary image of the preprocessed image; if the first glass image has image defects, performing closed operation processing on the first glass image to obtain a second glass image which is a defect-free connected glass image; and subtracting the first glass image from the second glass image to obtain a defect glass image representing the shape of the defect.
In one implementation, the image preprocessing is performed on the captured image, and includes:
carrying out image digitization processing, image geometric transformation processing, image normalization processing, image smoothing processing, image restoration processing and image enhancement processing on the shot image in sequence; the image digitization processing is used for acquiring a data image which can be processed by a computer, the image geometric transformation processing is used for correcting random errors of the shot image, the image normalization processing is used for eliminating invariance of the shot image, the image smoothing processing is used for eliminating noise of the shot image, the image restoration processing is used for correcting image degradation of the shot image, and the image enhancement processing is used for enhancing visual effects of the shot image.
In one implementation, the image segmentation processing is performed on the preprocessed image, and includes:
sequentially carrying out binarization processing and segmentation processing on the preprocessed image; wherein, the binarization processing is to set the gray value of the pixel point of the preprocessed image as 0 or 255; the segmentation processing is to perform gray threshold segmentation through a formula II;
the formula II is as follows:
Figure 177846DEST_PATH_IMAGE001
wherein
Figure 98660DEST_PATH_IMAGE002
A set of image elements representing the pre-processed image;
Figure 667045DEST_PATH_IMAGE003
a set of image elements representing a background image; t represents the gray level threshold of the image, x represents the abscissa of the pixel point, and y represents the ordinate of the pixel point.
In one embodiment, the method, after obtaining the first glass image, comprises:
acquiring a standard image, and calculating a correlation coefficient of the first glass image and the standard image through a formula I; if the correlation coefficient is larger than or equal to the coefficient threshold value, determining that the first glass image has image defects;
the formula I is as follows:
Figure 24208DEST_PATH_IMAGE004
wherein NCC represents an image correlation coefficient;
Figure 437871DEST_PATH_IMAGE005
representing a set of image elements
Figure 446148DEST_PATH_IMAGE006
Figure 591958DEST_PATH_IMAGE007
Representing a set of image elements
Figure 721238DEST_PATH_IMAGE008
Representing a vector dimension;
Figure 735330DEST_PATH_IMAGE009
representing a set of image elements
Figure 365157DEST_PATH_IMAGE010
Standard deviation of (d);
Figure 416290DEST_PATH_IMAGE011
represents the standard deviation of the set of image elements t;
Figure 528471DEST_PATH_IMAGE012
representing a set of image samples
Figure 956041DEST_PATH_IMAGE010
The mean value of (a);
Figure 109549DEST_PATH_IMAGE013
and the mean value of the image sample set t is represented, x represents the abscissa of the pixel point, and y represents the ordinate of the pixel point.
In one implementation, the closing operation process is performed on the first glass image, and includes:
sequentially carrying out image expansion processing and image corrosion processing on the first glass image; performing image expansion processing on the first glass image based on a formula III to obtain an expanded glass image;
the formula III is as follows:
Figure 925058DEST_PATH_IMAGE014
carrying out image corrosion treatment on the expanded glass image based on a formula IV to obtain a second glass image;
Figure 993377DEST_PATH_IMAGE015
a denotes a set of picture elements and B denotes a set of moving picture elements.
In one implementation, subtracting the second glass image from the first glass image comprises:
subtracting the first glass image from the second glass image by a formula five;
the formula five is as follows:
Figure 959059DEST_PATH_IMAGE016
wherein,
Figure 671800DEST_PATH_IMAGE017
set of picture elements representing a defective glass image
Figure 18730DEST_PATH_IMAGE018
Set of image elements representing a second glass image
Figure 590657DEST_PATH_IMAGE019
Set of image elements representing a first glass image
Figure 687926DEST_PATH_IMAGE020
X represents the abscissa of the pixel, and y represents the ordinate of the pixel.
In one embodiment, the method, after obtaining a defective glass image representing a shape of the defect, comprises:
and establishing a Cartesian rectangular coordinate system by taking the central point of the defective glass image as a coordinate origin, extracting the pixel point coordinates of the defective glass image to obtain a coordinate set, wherein the coordinate set is the coordinate set of all the pixel points of the defective glass image.
In one implementation, after obtaining the coordinate set, the method further includes:
and classifying the defect of the defective glass image by using a convolutional neural network to obtain the defect type of the defective glass image, wherein the convolutional neural network is a network model for classifying the defect type of the defective image.
In one embodiment, the method further comprises, after obtaining the defect type of the defective glass image:
and transmitting the defect type and the defect glass image to a CIM computer integrated manufacturing system and a cloud database based on a wireless network.
A second aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A third aspect of the application provides a non-transitory machine-readable storage medium having stored thereon executable code which, when executed by a processor of an electronic device, causes the processor to perform a method as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
through automatic cutting glass edge image detection, avoided the error that arouses by artifical measurement, can promote the product detection efficiency of glass production line, and then reduce because of the uneven risk that leads to defective glass product to flow into market of cutting, improve product quality.
The technical scheme of the application can also be as follows:
the type of the glass defect and the position information of the defect on the glass are determined through further analysis and calculation, and a tool for cutting the glass is replaced or adjusted in time, so that the defect generated by glass cutting is avoided from the source; meanwhile, the types of the defects of the glass and the position information of the defects on the glass are uploaded to a data center to form cloud big data, and when the same conditions are met, the shot images are compared, the detection process is reduced, the detection result is obtained quickly, and the working efficiency is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
FIG. 1 is a schematic flow chart diagram illustrating a method for intelligently detecting defective glass images in accordance with an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating a method for determining the presence of image defects in an image for intelligently detecting defective glass images according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for detecting defect types for intelligently detecting defective glass images according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
To above-mentioned problem, this application embodiment provides a method of intellectual detection system defect glass image, detects cutting glass edge image through automatic, has avoided the error that arouses by artifical measurement, can promote the product detection efficiency of glass production line, and then reduces the risk that leads to the defective glass product to flow into market because of the cutting is uneven, improves product quality.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for intelligently detecting a defective glass image according to an embodiment of the present application.
Referring to fig. 1, an embodiment (embodiment one) of the method for intelligently detecting a defective glass image in the embodiment of the present application includes:
101. acquiring a shot image of glass to be detected;
in this embodiment, in the captured image of the glass to be measured, the glass to be measured is the glass after being cut and separated, and each piece of glass has a corresponding product serial number; in order to improve the quality of glass products delivered from factories, the glass of a cutting surface needs to be detected, and the information of the cutting surface needs to be recorded; for example, a product serial number of a glass product is identified through a code reader, and an image of the cut glass edge (namely, a shot image of the glass to be measured) is acquired by an image sensor; the glass to be detected is a regular rectangular panel, and is provided with four cutting surfaces, each cutting surface needs to be detected, and each cutting surface needs to acquire two images which are images on two long sides of the cutting surface; therefore, the shot images of the glass to be detected are generally 8 images, each image has a corresponding serial number, the images detected subsequently are better distinguished, and data traceability is achieved.
102. Carrying out image preprocessing on the shot image to obtain a preprocessed image;
in this embodiment, since the shot image has a lot of information that affects the judgment of the defect, the shot image needs to be subjected to image preprocessing to remove information irrelevant to the judgment of the defect, so as to facilitate entering the next process; in general, the types of the acquired final images are different, and the information for removing the image preprocessing is also different, in this example, the purpose of performing the image preprocessing is to remove all the irrelevant information with the defect image, and specifically includes: sequentially carrying out image digitization processing, image geometric transformation processing, image normalization processing, image smoothing processing, image restoration processing and image enhancement processing on the shot image;
the image digitization processing is used for acquiring a data image which can be processed by a computer, for example, the original gray value of the shot image is generally a continuous function of a space variable, so that the gray value of the image can be sampled and quantized on a space lattice of pixel points of the shot image, and a digital image which can be processed by the computer can be obtained;
the image geometric transformation processing is used for correcting random errors of the shot image, and after the digital image which can be processed by a computer is obtained, the digital image needs to be further corrected; for example, errors in the digital image due to natural conditions or the capture device can be represented by a model and eliminated by geometric transformation, such as by comparing the digital image with an image of known correct geometric position, the transformation being achieved by solving a set of bivariate polynomial functions with a number of control points; the Data Image (Image Data) is a set of gradation values of each Pixel (Pixel) expressed as a numerical value.
The image normalization processing is used for eliminating invariance of the shot image, and properties such as the area and the perimeter of the shot image have invariance properties for coordinate rotation, under specific conditions, specific factors or transformation can affect the properties of the shot image, in order to avoid the influence, the invariant properties of the shot image are eliminated or weakened through normalization processing, so that the quality of the detected image is improved, and it is noted that the normalization processing adopted in the embodiment is gray level normalization, and the gray level transformation normalization is to expand the gray level distribution in the original image to an image with the whole gray level by using a gray level stretching method;
the image smoothing processing is used for eliminating the noise of the shot image, which is to avoid blurring of the image contour or lines, so as to improve the quality of the detected image, and in practical applications, the image smoothing processing methods include a median method, a local averaging method, a k-nearest neighbor averaging method, a spatial frequency domain band-pass filtering method, and the like, and in this example, any one of the methods can be used for processing;
the image restoration processing is used for correcting the image degradation of the shot image, and aims to ensure the image quality of the shot image during detection, so that the accuracy of image detection is improved; for example, an appropriate restoration filter (i.e., an inverse filtering process) is designed to realize image restoration, and if f (x, y) represents a static two-dimensional image, which is degraded into g (x, y) after passing through the system h (x, y) under the interference of external noise n (x, y), the restored image is f (x, y); when the original image lacks necessary prior knowledge, a model is established in the degradation process, a rough description is firstly carried out on the model, and then the model is corrected gradually and reasonably according to specific conditions in the restoration process to gradually eliminate the error influence; when the original image has enough prior knowledge, an accurate mathematical model is directly established for the original image at this time, and then the degraded image is subjected to restoration processing.
The image enhancement processing is used for enhancing the visual effect of the shot image, and in the actual processing, the information in the image is selectively enhanced and suppressed so as to achieve the purpose of improving the visual effect of the image, or the image is converted into a form more suitable for machine processing so as to facilitate data extraction or identification; for example, an image enhancement system may highlight the contour of an image through a high-pass filter, so that a machine can measure the shape and the circumference of the contour, and there are various methods for image enhancement, specifically, methods such as contrast widening, logarithmic transformation, density layering, a spatial domain method, histogram equalization, and the like, which are all used to change the gray tone and highlight details of the image in practical applications, in this case, the spatial domain method is used to enhance the visual effect of the captured image.
103. Carrying out image segmentation processing on the preprocessed image to obtain a first glass image, wherein the first glass image is a binary image of the preprocessed image;
in this embodiment, the preprocessed image refers to an image obtained after preprocessing the captured image; after the preprocessed image is obtained, in order to further divide the image, so that the image of the defect part is more obvious, and the image of the defect part can be distinguished, image segmentation processing needs to be performed on the preprocessed image; the image segmentation processing means that binarization processing and segmentation processing are sequentially carried out on the preprocessed image; the binarization processing is to set the gray value of a pixel point on an image to be 0 or 255, so as to enable the whole image to have an obvious black-and-white effect, greatly reduce the data volume in the image and further highlight the outline of a target; performing segmentation processing after the binarization processing is finished, wherein the segmentation processing refers to the step of segmenting the image after the binarization processing by setting a threshold value; for example, the threshold value parameter of the gray value is set to 40, if the gray value is greater than 40, the image is divided into the gray values of the target glass defect image, if the gray value is less than 40, the image is divided into the gray values of the background image, and after the division process is completed, the binary image of the glass (i.e., the first glass image) can be obtained.
It is noted that there is a standard expression, formula two, for the segmentation process; in practical application, when performing threshold segmentation processing, the processing is performed according to formula two, and the following is an expression of formula two:
Figure 645386DEST_PATH_IMAGE021
wherein,
Figure 802698DEST_PATH_IMAGE022
representing picture elements to be segmentedA set of elements;
Figure 596342DEST_PATH_IMAGE023
a set of image elements representing a background image; t represents a self-defined image gray threshold, x represents the abscissa of the pixel point, and y represents the ordinate of the pixel point.
104. If the first glass image has image defects, performing closed operation processing on the first glass image to obtain a second glass image, wherein the second glass image is a defect-free connected glass image;
in this embodiment, when the first glass image (i.e., the binarized image) has an image defect, since the binarized image cannot directly determine the image of the defective portion, further operation is required to determine the image of the defective portion; after the image segmentation processing, the gray value of the defect part is in a blank state, and in order to enable the blank part to be an image, the first glass image needs to be subjected to closing operation processing, wherein the closing operation processing is to perform pixel expansion and then perform pixel corrosion on the first glass image; the closing operation is usually used to make up for narrow discontinuities and long narrow gaps, eliminate smaller voids, and fill up fractures in the contour lines; after the closing operation, a plurality of adjacent image blocks can be connected, wherein the connection of the image blocks is called a projection-free connected domain, namely, a blank part in the image is filled to obtain a defect-free image;
in the closed operation processing, the expansion refers to the operation of "lengthening" or "thickening" in the binary image, and this special operation is controlled by a set called a structural element (i.e. another image element set), the structural element is often represented by a matrix of 0 and 1 during calculation, and the origin of the structural element must be clearly marked, after the structural element is determined, the origin of the structural element is translated through the whole binary image area, and the image after the expansion is obtained; it is to be noted that, when the image expansion processing is performed, based on the processing of formula three, the following is an expression of formula three:
Figure 497302DEST_PATH_IMAGE024
in the closed operation treatment, the corrosion refers to that the edge and the protruding part of the connected domain are flattened on the expanded image, and finally, a binaryzation image of the connected domain without the protrusion is obtained; similar to the expansion process, the corrosion process is controlled by a structural element, and the structural element is used for translating the protruding area in the whole binary image to obtain a defect-free connected glass image without the protruding connected area after the corrosion is finished; it is to be noted that, when the image erosion processing is performed, based on the formula four processing, the following is an expression of the formula four:
Figure 435169DEST_PATH_IMAGE025
wherein, in formula three and formula four, a represents a set of elements of the binarized image, B represents a set of elements of the other image, and Z represents a moving distance of the moving image element set.
105. And subtracting the first glass image from the second glass image to obtain a defect glass image representing the shape of the defect.
In this embodiment, after obtaining the second glass image (i.e., defect-free connected glass image), further processing is required to obtain the target image in order to obtain the defective glass image; that is, the second glass image is subtracted from the first glass image (i.e., the binarized image) to obtain a defective glass image representing the shape of the defect; subtracting the first glass image (i.e., the binary image) from the second glass image (i.e., subtracting the pixel corresponding to the first glass image from the pixel corresponding to the second glass image) according to formula five;
the formula five is as follows:
Figure 435486DEST_PATH_IMAGE026
wherein,
Figure 198649DEST_PATH_IMAGE027
set of picture elements representing a defective glass image
Figure 903300DEST_PATH_IMAGE028
Set of image elements representing a second glass image
Figure 586085DEST_PATH_IMAGE029
Set of image elements representing a first glass image
Figure 85200DEST_PATH_IMAGE030
X represents the abscissa of the pixel, and y represents the ordinate of the pixel.
Fig. 2 is a flowchart illustrating a method for intelligently detecting a defective glass image to determine the presence of an image defect in the image according to an embodiment of the present application.
Referring to fig. 2, a second embodiment (embodiment two) of the method for intelligently inspecting a defective glass image in the embodiment of the present application includes:
201. acquiring a standard image, and calculating a correlation coefficient of the first glass image and the standard image based on a formula I;
in the present embodiment, the standard image refers to a defect-free glass image, which is determined according to the quality requirement of the customer for the image; in order to determine whether the first glass image (i.e., the binary image) is a defective image, calculating a correlation coefficient between a standard image and the first glass image (i.e., the binary image), and determining whether the first glass image is a defective image according to the magnitude of the correlation coefficient; in practical applications, the correlation coefficient is calculated according to formula one, and the following is an expression of formula one:
Figure 837124DEST_PATH_IMAGE031
wherein NCC represents a correlation coefficient of the standard image and the first glass image;
Figure 220832DEST_PATH_IMAGE032
a set of elements representing a first glass image;
Figure 617178DEST_PATH_IMAGE033
a set of elements representing a standard image; n represents a vector dimension;
Figure 913293DEST_PATH_IMAGE034
representing a standard deviation of a set of elements of a first glass image;
Figure 293459DEST_PATH_IMAGE036
a collective standard deviation of a set of elements representing a standard image;
Figure 949699DEST_PATH_IMAGE038
a mean value representing a set of elements of the first glass image;
Figure 856344DEST_PATH_IMAGE040
the mean value of the element set of the standard image is represented, x represents the abscissa of the pixel point, and y represents the ordinate of the pixel point.
202. And if the correlation coefficient is larger than or equal to a coefficient threshold value, determining that the first glass image has image defects.
In this embodiment, after the correlation coefficient is calculated, it is necessary to determine whether the first glass image (i.e., the binarized image) is an image defect by comparing a coefficient threshold value, and if the correlation coefficient is greater than or equal to the coefficient threshold value, it is determined that the first glass image is a defective glass image, i.e., the first glass image has an image defect; if the correlation coefficient is smaller than the coefficient threshold value, determining that the first glass image is a qualified glass image, namely the first glass image has no image defect and belongs to a qualified product; the coefficient threshold value can be changed according to the requirements of customers, the higher the quality of the product is, the higher the coefficient threshold value is, and the lower the quality of the product is, the lower the coefficient threshold value is.
In practical application, the coefficient threshold value can be determined according to an empirical value, wherein the empirical value is a threshold value which is generated for the most times in the historical glass image detection process; it should be noted that the values of the coefficient threshold and the correlation coefficient are between 0 and 100, for example, assuming that the coefficient threshold at which the number of times of glass image detection occurs most is 70, the empirical value is determined to be 70, if not requested by the customer, the empirical value is taken as the coefficient threshold, and when the calculated correlation coefficient is greater than or equal to 70, the first glass image is determined to be a defective glass image; when the calculated correlation coefficient is less than 70, the first glass image is determined to be a passing glass image.
Fig. 3 is a flowchart illustrating a method for intelligently detecting a defective glass image to detect a defect type according to an embodiment of the present application.
Referring to fig. 3, a third embodiment (embodiment three) of the method for intelligently detecting a defective glass image in the embodiment of the present application includes:
301. establishing a Cartesian rectangular coordinate system by taking the central point of the defective glass image as a coordinate origin, extracting pixel point coordinates of the defective glass image to obtain a coordinate set, wherein the coordinate set is the coordinate set of all pixel points of the defective glass image;
in the embodiment, in order to determine the defect position of the defect image conveniently, the defect image needs to be positioned, and the positioning of the defect image is used for quickly finding out the defect position of a glass product, so that the solid repair and the finding and determining of the defect reason causing the cutting edge of the glass are conveniently realized, and the product error rate of cutting the glass is reduced; the image acquired by the sensor is a rectangular image, four corners are arranged in the rectangular image, the intersection point of diagonal lines is taken as a central point, in this example, the central point is set as the coordinate origin of a Cartesian rectangular coordinate system, the coordinate positions of all Pixels (Pixels) in the rectangular image can be determined according to the coordinate origin, the distance from each Pixel point to the coordinate origin can be determined according to each Inch of Pixels (Pixels Per Inc), and the coordinate positions of the Pixels in the defect image can be determined; it is worth noting that each defective image has N pixel points, so that the pixel point coordinates of the defective glass image are set coordinates, and the position of the defect of the cutting surface of the glass product corresponding to the defective glass image can be determined according to any one coordinate of the set coordinates.
Wherein, a Cartesian coordinate system (Cartesian coordinates) is a general name of a rectangular coordinate system and an oblique coordinate system, and two axes intersecting at an origin form a plane radial coordinate system; pixels (all called as image elements in chinese) are the size unit of resolution, which refers to the basic coding of the basic primary color elements and their gray levels, and constitute the basic unit of digital image, and usually the size of the resolution of the image is expressed in units of ppi (pixel per inch).
302. Classifying the defects of the defective glass images by using a convolutional neural network to obtain the defect types of the defective glass images, wherein the convolutional neural network is a network model for classifying the defect types of the defective images;
in this embodiment, after obtaining the defective glass image and the coordinate set, further analysis and determination are required to determine which defect type the defective glass image is; knowing the defect type of the defective glass image can quickly determine the cause of the defect, and in glass cutting, cutting defects can be caused by a cutting knife, a cutting position and cutting time, so that the defect type is determined to be a necessary detection step; in this example, the defect type is determined by analysis of a convolutional neural network, and the defect glass image is transmitted to the convolutional neural network, i.e., the defect type can be analyzed.
Notably, the Convolutional Neural Networks (CNN) is a type of feed-forward Neural network that contains convolution calculations and has a deep structure; the convolutional neural network constructs different feature vectors (by the features of different defect types) according to the defective glass image to analyze; wherein the extracted traits comprise: the length, width, contrast, gray level, textural features, entropy, gradient and the like of the defective glass image are identified in a multi-dimensional manner by utilizing a convolutional neural network, so that the defect type can be obtained.
303. And transmitting the defect type and the defect glass image to a CIM computer integrated manufacturing system and a cloud database based on a wireless network.
In this embodiment, after obtaining the defect type of the defective glass image and the coordinate set of the defective glass image, in order to store and record the detection data, information such as the serial number, the defect type, the defective glass image transmission, the coordinate set, and the like of the glass image needs to be transmitted to the CIM integrated computer manufacturing system and the cloud database; and the data transmission is realized by uploading the detection information to a factory CIM system and a cloud database by using a 5G wireless network.
It is worth noting that the method further comprises the steps of processing, identifying and displaying relevant information of the acquired defective glass image based on the terminal device, so that monitoring of operators is facilitated, and labor cost is reduced; the terminal equipment can also be connected with a plurality of mobile terminal equipment through the 5G transmission equipment. After the related information is transmitted to the cloud database, data samples of the big data platform can be added (namely training samples of the convolutional neural network are added), and through data analysis and processing of the big data platform, when the big data platform receives the same related information, results of the detected image are directly fed back, the effect of shortening the detection time is achieved, and the working efficiency is improved; meanwhile, according to the result obtained by analyzing and processing the measurement and detection data of the defective glass image, the operator of the upstream cutting equipment can be informed to replace the cutting gear according to the detection result, so that the occurrence of defects is reduced, and the production is optimized.
The CIM Computer Integrated manufacturing system (Computer Integrated manufacturing-manufacturing) comprises a system which is Integrated for practical reasons for various technical functions and management functions necessary for producing products through the information technology cooperative work among production planning and control, Computer aided design, Computer aided process planning, Computer aided manufacturing and Computer aided quality management; the 5G wireless network transmission can transmit data at high speed and with low delay, so that the working efficiency is improved; the cloud database is used for storing and comparing the cut glass defect image information, and the optimized detection speed can be accelerated.
Corresponding to the foregoing embodiment of the application function implementation method, the present application further provides an electronic device and a corresponding embodiment (embodiment four).
Fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 4, the electronic device 1000 includes a memory 1010 and a processor 1020.
The Processor 1020 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 1010 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are needed by the processor 1020 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, among others. In some embodiments, memory 1010 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 1010 has stored thereon executable code that, when processed by the processor 1020, may cause the processor 1020 to perform some or all of the methods described above.
The aspects of the present application have been described in detail hereinabove with reference to the accompanying drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required in the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiment of the present application may be combined, divided, and deleted according to actual needs.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the present application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the applications disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (10)

1. A method for intelligently detecting a defective glass image is characterized by comprising the following steps:
acquiring a shot image of glass to be detected;
carrying out image preprocessing on the shot image to obtain a preprocessed image;
carrying out image segmentation processing on the preprocessed image to obtain a first glass image, wherein the first glass image is a binary image of the preprocessed image;
acquiring a standard image, and calculating a correlation coefficient of the first glass image and the standard image through a formula I;
if the correlation coefficient is larger than or equal to a coefficient threshold value, determining that the first glass image has image defects;
the formula I is as follows:
Figure 132214DEST_PATH_IMAGE002
wherein NCC represents an image correlation coefficient;
Figure 580513DEST_PATH_IMAGE004
representing a set of image elements
Figure 891408DEST_PATH_IMAGE006
Representing a set of image elements t; n represents a vector dimension;
Figure 67044DEST_PATH_IMAGE008
representing a set of image elements
Figure 412574DEST_PATH_IMAGE010
Standard deviation of (d);
Figure 766195DEST_PATH_IMAGE012
represents the standard deviation of the set of image elements t;
Figure 564387DEST_PATH_IMAGE014
representing a set of image elements
Figure 45178DEST_PATH_IMAGE016
The mean value of (a);
Figure 510794DEST_PATH_IMAGE018
representing the mean value of the image element set t, x representing the abscissa of the pixel point, and y representing the ordinate of the pixel point;
if the first glass image has image defects, performing closed operation processing on the first glass image to obtain a second glass image, wherein the second glass image is a defect-free connected glass image;
and subtracting the first glass image from the second glass image to obtain a defect glass image representing the shape of the defect.
2. The method of claim 1, wherein the image pre-processing the captured image comprises:
sequentially carrying out image digitization processing, image geometric transformation processing, image normalization processing, image smoothing processing, image restoration processing and image enhancement processing on the shot image;
the image digitization processing is used for acquiring a data image which can be processed by a computer, the image geometric transformation processing is used for correcting random errors of the shot image, the image normalization processing is used for eliminating invariance of the shot image, the image smoothing processing is used for eliminating noise of the shot image, the image restoration processing is used for correcting image degradation of the shot image, and the image enhancement processing is used for enhancing visual effect of the shot image.
3. The method according to claim 1, wherein the performing image segmentation processing on the preprocessed image comprises:
sequentially carrying out binarization processing and segmentation processing on the preprocessed image;
the binarization processing is to set the gray value of a pixel point of the preprocessed image to be 0 or 255;
the segmentation processing is to perform gray threshold segmentation through a formula II;
the formula II is as follows:
Figure 35317DEST_PATH_IMAGE020
wherein
Figure 320804DEST_PATH_IMAGE022
A set of image elements representing the pre-processed image;
Figure 569733DEST_PATH_IMAGE024
a set of image elements representing a background image; t represents the gray level threshold of the image, x represents the abscissa of the pixel point, and y represents the ordinate of the pixel point.
4. The method of claim 1, wherein said processing the first glass image in a close operation comprises:
sequentially carrying out image expansion processing and image corrosion processing on the first glass image;
performing image expansion processing on the first glass image based on a formula III to obtain an expanded glass image;
the formula III is as follows:
Figure 889856DEST_PATH_IMAGE026
carrying out image corrosion treatment on the expanded glass image through a formula IV to obtain a second glass image;
the formula four is as follows:
Figure 850859DEST_PATH_IMAGE028
a denotes a set of image elements, B denotes a set of moving image elements, and Z denotes a moving distance of the set of moving image elements.
5. The method of claim 1, wherein subtracting the first glass image from the second glass image comprises:
subtracting the first glass image from the second glass image by a formula five;
the formula five is as follows:
Figure 623643DEST_PATH_IMAGE030
wherein,
Figure 180657DEST_PATH_IMAGE032
set of picture elements representing a defective glass image
Figure 355287DEST_PATH_IMAGE034
Set of image elements representing a second glass image
Figure 956032DEST_PATH_IMAGE036
Set of image elements representing a first glass image
Figure 481692DEST_PATH_IMAGE038
X represents the abscissa of the pixel, and y represents the ordinate of the pixel.
6. The method of claim 1, wherein said obtaining a defective glass image representing a shape of the defect comprises:
and establishing a Cartesian rectangular coordinate system by taking the central point of the defective glass image as a coordinate origin, extracting pixel point coordinates of the defective glass image to obtain a coordinate set, wherein the coordinate set is the coordinate set of all pixel points of the defective glass image.
7. The method of claim 6, wherein after obtaining the set of coordinates, further comprising:
and classifying the defects of the defective glass images by using a convolutional neural network to obtain the defect types of the defective glass images, wherein the convolutional neural network is a network model for classifying the defect types of the defective images.
8. The method of claim 7, wherein after obtaining the defect type of the defective glass image, further comprising:
and transmitting the defect type and the defect glass image to a CIM computer integrated manufacturing system and a cloud database based on a wireless network.
9. An electronic device, comprising:
a processor; and the number of the first and second groups,
a storage having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1-8.
10. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-8.
CN202110398702.XA 2021-04-14 2021-04-14 Method for intelligently detecting defective glass image, electronic device and storage medium Active CN112802022B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110398702.XA CN112802022B (en) 2021-04-14 2021-04-14 Method for intelligently detecting defective glass image, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110398702.XA CN112802022B (en) 2021-04-14 2021-04-14 Method for intelligently detecting defective glass image, electronic device and storage medium

Publications (2)

Publication Number Publication Date
CN112802022A true CN112802022A (en) 2021-05-14
CN112802022B CN112802022B (en) 2021-10-29

Family

ID=75811381

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110398702.XA Active CN112802022B (en) 2021-04-14 2021-04-14 Method for intelligently detecting defective glass image, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN112802022B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114764804A (en) * 2022-06-16 2022-07-19 深圳新视智科技术有限公司 Lithium battery pole piece defect detection method, device, equipment and storage medium
CN115610739A (en) * 2022-09-26 2023-01-17 江阴瑞兴塑料玻璃制品有限公司 Bubble state detection platform for glass film pasting machine

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1482579A (en) * 2002-09-13 2004-03-17 ��ʿͨ��ʽ���� Image defect inspecting apparatus and image defect inspecting method
US20060029257A1 (en) * 2004-08-03 2006-02-09 Honda Motor Co., Ltd. Apparatus for determining a surface condition of an object
CN102020036A (en) * 2010-11-02 2011-04-20 昆明理工大学 Visual detection method for transparent paper defect of outer package of strip cigarette
US20150215558A1 (en) * 2013-01-07 2015-07-30 Canon Kabushiki Kaisha Image capturing apparatus and method for controlling the same
CN106204618A (en) * 2016-07-20 2016-12-07 南京文采科技有限责任公司 Product surface of package defects detection based on machine vision and sorting technique
CN106780438A (en) * 2016-11-11 2017-05-31 广东电网有限责任公司清远供电局 Defects of insulator detection method and system based on image procossing
CN107169967A (en) * 2017-07-07 2017-09-15 哈尔滨理工大学 A kind of diamond saw blade crack detecting method based on image procossing
CN111583258A (en) * 2020-05-28 2020-08-25 常州节卡智能装备有限公司 Defect detection method, device, system and storage medium
CN112184744A (en) * 2020-11-29 2021-01-05 惠州高视科技有限公司 Display screen edge defect detection method and device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1482579A (en) * 2002-09-13 2004-03-17 ��ʿͨ��ʽ���� Image defect inspecting apparatus and image defect inspecting method
US20060029257A1 (en) * 2004-08-03 2006-02-09 Honda Motor Co., Ltd. Apparatus for determining a surface condition of an object
CN102020036A (en) * 2010-11-02 2011-04-20 昆明理工大学 Visual detection method for transparent paper defect of outer package of strip cigarette
US20150215558A1 (en) * 2013-01-07 2015-07-30 Canon Kabushiki Kaisha Image capturing apparatus and method for controlling the same
CN106204618A (en) * 2016-07-20 2016-12-07 南京文采科技有限责任公司 Product surface of package defects detection based on machine vision and sorting technique
CN106780438A (en) * 2016-11-11 2017-05-31 广东电网有限责任公司清远供电局 Defects of insulator detection method and system based on image procossing
CN107169967A (en) * 2017-07-07 2017-09-15 哈尔滨理工大学 A kind of diamond saw blade crack detecting method based on image procossing
CN111583258A (en) * 2020-05-28 2020-08-25 常州节卡智能装备有限公司 Defect detection method, device, system and storage medium
CN112184744A (en) * 2020-11-29 2021-01-05 惠州高视科技有限公司 Display screen edge defect detection method and device

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
徐光柱等著: "相似度计算", 《实用性目标检测与跟踪算法原理与应用》 *
汪为巍著: "形态学图像处理基本运算", 《膨胀土裂隙演化三维分布特征及微观结构分形规律研究》 *
赵小川著: "腐蚀与膨胀", 《MATLAB图像处理 程序实现与模块化仿真 第2版》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114764804A (en) * 2022-06-16 2022-07-19 深圳新视智科技术有限公司 Lithium battery pole piece defect detection method, device, equipment and storage medium
CN115610739A (en) * 2022-09-26 2023-01-17 江阴瑞兴塑料玻璃制品有限公司 Bubble state detection platform for glass film pasting machine
CN115610739B (en) * 2022-09-26 2023-05-16 江阴瑞兴塑料玻璃制品有限公司 Glass film pasting machinery bubble state detection platform

Also Published As

Publication number Publication date
CN112802022B (en) 2021-10-29

Similar Documents

Publication Publication Date Title
CN109580630B (en) Visual inspection method for defects of mechanical parts
US10330608B2 (en) Systems and methods for wafer surface feature detection, classification and quantification with wafer geometry metrology tools
JP4657869B2 (en) Defect detection apparatus, image sensor device, image sensor module, image processing apparatus, digital image quality tester, defect detection method, defect detection program, and computer-readable recording medium
CN113570605B (en) Defect detection method and system based on liquid crystal display panel
US9846929B2 (en) Fast density estimation method for defect inspection application
CN112802022B (en) Method for intelligently detecting defective glass image, electronic device and storage medium
WO2024002187A1 (en) Defect detection method, defect detection device, and storage medium
CN116777907A (en) Sheet metal part quality detection method
TW201512649A (en) Method of chip detects inspecting, system therefor, and computer program product thereof
CN117495856B (en) Wafer surface detection method, device, equipment and medium based on deep learning
WO2021046726A1 (en) Method and device for detecting mechanical equipment parts
CN114332026A (en) Visual detection method and device for scratch defects on surface of nameplate
CN116485779B (en) Adaptive wafer defect detection method and device, electronic equipment and storage medium
CN112102254A (en) Wood surface defect detection method and system based on machine vision
CN112488998A (en) Apple stem and calyx detection method based on stripe projection
CN112014407A (en) Method for detecting surface defects of integrated circuit wafer
CN114581805A (en) Coating roller surface defect detection method adopting 3D line laser profile technology
CN117237747A (en) Hardware defect classification and identification method based on artificial intelligence
Sarı et al. Deep learning application in detecting glass defects with color space conversion and adaptive histogram equalization
CN114187269B (en) Rapid detection method for surface defect edge of small component
TWI757590B (en) Luminance uniform detection system and luminance uniform detection method
CN113870328A (en) Liquid foreign matter visual detection method and system
CN116485350B (en) Intelligent production system of medium borosilicate glass based on image recognition
JP2006135700A (en) Image inspection device, image inspection method, control program and readable storage medium
CN117934453B (en) Method and system for diagnosing defects of backlight foreign matters of mobile phone screen

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 215163 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou City, Jiangsu Province

Applicant after: Gaoshi Technology (Suzhou) Co.,Ltd.

Address before: 516000 west side of the fourth floor, building CD, science and technology entrepreneurship center, No.2, South Huatai Road, Huinan hi tech Industrial Park, huiao Avenue, Huicheng District, Huizhou City, Guangdong Province

Applicant before: HUIZHOU GOVION TECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: 215129 Rooms 101, 102, 901, 902, Floor 9, Building 11, No. 198, Jialing River Road, High tech Zone, Suzhou City, Jiangsu Province

Patentee after: Gaoshi Technology (Suzhou) Co.,Ltd.

Address before: 215163 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou City, Jiangsu Province

Patentee before: Gaoshi Technology (Suzhou) Co.,Ltd.